3rd Place Scheme on Instance Segmentation Track of ICCV 2021 VIPriors Challenges. (arXiv:2110.00242v5 [cs.CV] UPDATED)

In this paper, we introduce a data-efficient instance segmentation method we
used in the 2021 VIPriors Instance Segmentation Challenge. Our solution is a
modified version of Swin Transformer, based on the mmdetection which is a
powerful toolbox. To solve the problem of lack of data, we utilize data
augmentation including random flip and multiscale training to train our model.
During inference, multiscale fusion is used to boost the performance. We only
use a single GPU during the whole training and …

arxiv challenges iccv segmentation